2 papers
cs.CV2026
Decoupled Guidance: Disentangling Subject and Context Pathways in Text-to-Image Personalization
Seongmin Kim, Kyucheol Shin, Heesun Jung +2
Text-to-image personalization aims to generate a user-provided subject in novel scenes described by text. However, most existing methods encode subject identity (fidelity) and cont…
cs.CV2026
Training-Free Debiasing of Diffusion Models via CLIP-Guided Denoising Optimization
Dain Kim, Jinseo Kim, Sungyong Baik
Text-to-image diffusion models achieve impressive visual quality, yet demographic bias remains a challenge, as neutral prompts consistently produce stereotypical representations ac…